Data science

In the last two lecturs, we discuss a general model for learning, neural networks.

History and recent surge

From Wang and Raj (2017):

Learning sources

Single layer neural network

Multi-layer neural network

Practical issues

Neural networks are not a fully automatic tool, as they are sometimes advertised; as with all statistical models, subject matter knowledge should and often be used to improve their performance.

Convoluted neural networks (CNN)

Sources: https://colah.github.io/posts/2014-07-Conv-Nets-Modular/

Example: handwritten digit recognition.

network links weights accuracy
net 1 2570 2570 80.0%
net 2 3124 3214 87.0%
net 3 1226 1226 88.5%
net 4 2266 1131 94.0%
net 5 5194 1060 98.4%

Example: image classification

Recurrent neural networks (RNN)

Souces: https://colah.github.io/posts/2015-08-Understanding-LSTMs/ http://karpathy.github.io/2015/05/21/rnn-effectiveness/